Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    a response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மனதில்
    0.59
    hounds
    0.54
    EtOH
    0.53
    शुदा
    0.53
     bioquímica
    0.53
     potência
    0.52
     اکرم
    0.51
    pubescens
    0.50
     соци
    0.49
     अँ
    0.48
    POSITIVE LOGITS
    s
    0.69
    ii
    0.67
     dazu
    0.61
    ib
    0.59
     d
    0.58
     das
    0.58
     gyd
    0.57
    ي
    0.56
    iu
    0.55
     staat
    0.55
    Act Density 0.002%

    No Known Activations